Techniques for product recommendation involve receiving, from a user, a text input expressing a question asking for a product recommendation. In response to the question, an answer that identifies a product for recommendation to the user may be generated. A plurality of product reviews comprising natural language text evaluations of the product may be analyzed, involving identifying at least one passage of text in at least one of the product reviews as providing supporting evidence for the product in answer to the question. The answer and the at least one passage in the at least one product review identified as providing supporting evidence for the answer may be presented to the user in response to the text input.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method comprising: receiving, from a user, a text input expressing a question asking for recommendation of a product having a first requested characteristic and a second requested characteristic; identifying a product having the first requested characteristic, at least in part by locating in an ontology a node corresponding to the first requested characteristic, and traversing a relationship in the ontology from the node corresponding to the first requested characteristic to a node corresponding to the product; analyzing, using a natural language analysis component implemented via at least one processor, a plurality of product reviews comprising natural language text evaluations of the product identified from the ontology as having the first requested characteristic, including analyzing the natural language in at least one passage of text in at least one product review of the plurality of product reviews to determine whether the natural language in the at least one passage of text has a meaning indicating that the product also has the second requested characteristic; in response to determining via the natural language analysis that the natural language in the at least one passage of text has a meaning indicating that the product also has the second requested characteristic, identifying the at least one passage of text in the at least one product review as providing supporting evidence for the product in answer to the question; generating, in response to the question, an answer that identifies the product having the first and second requested characteristics for recommendation to the user; and presenting to the user, in response to the text input, the answer and the at least one passage in the at least one product review identified as providing supporting evidence for the answer.
The system recommends products based on user questions. It receives a text question asking for a product with two characteristics. It uses an ontology (a knowledge graph) to find a product with the first characteristic. It locates the node for the first characteristic and follows a relationship to a product node. Then, it analyzes product reviews using natural language processing. It checks if reviews for the found product indicate the product also has the second characteristic. If a review passage says the product has both characteristics, the system identifies that passage as supporting evidence. Finally, the system presents the recommended product and the supporting review passage to the user.
2. The method of claim 1 , wherein the at least one product review comprises an evaluation of the product made by a purchaser of the product.
The product recommendation method where the supporting review passage provided to the user in response to the text input expressing a question asking for recommendation of a product having a first requested characteristic and a second requested characteristic is an evaluation of the product made by a purchaser of the product.
3. The method of claim 1 , wherein the at least one product review comprises an evaluation of the product made based on use of the product by an author of the at least one product review.
The product recommendation method where the supporting review passage provided to the user in response to the text input expressing a question asking for recommendation of a product having a first requested characteristic and a second requested characteristic is an evaluation of the product made based on the reviewer's use of the product.
4. The method of claim 1 , further comprising retrieving the at least one passage in the at least one product review from at least one source selected from the group consisting of: user product reviews, expert product reviews, and social media.
The product recommendation method further retrieves the supporting review passage provided to the user in response to the text input expressing a question asking for recommendation of a product having a first requested characteristic and a second requested characteristic from user product reviews, expert product reviews, or social media posts.
5. The method of claim 1 , wherein the answer comprises information about the product, selected from the group consisting of: a name of the product, a brand of the product, a model identifier of the product, an image of the product, a price for the product, and identification of a merchant offering the product for sale.
In the product recommendation method, the product information provided to the user in response to the text input expressing a question asking for recommendation of a product having a first requested characteristic and a second requested characteristic, includes the product's name, brand, model identifier, image, price, or the merchant selling it.
6. The method of claim 1 , wherein analyzing the plurality of product reviews further comprises: scoring passages in at least some of the plurality of product reviews based at least in part on strength of the passages' supporting evidence for the product in answer to the question; and selecting the at least one passage in the at least one product review for presentation to the user based at least in part on the scoring.
This invention relates to analyzing product reviews to extract and present relevant information in response to user queries. The problem addressed is the difficulty of efficiently identifying and presenting the most informative and evidence-supported passages from a large volume of product reviews to answer specific user questions. The method involves processing a collection of product reviews to identify passages that provide strong supporting evidence for a product in response to a user's question. The analysis includes scoring passages based on the strength of their supporting evidence, where higher scores indicate stronger evidence. The scoring may consider factors such as the relevance of the passage to the question, the clarity of the evidence, and the credibility of the review source. After scoring, the method selects the highest-scoring passages from the reviews for presentation to the user, ensuring that the displayed information is both relevant and well-supported. This approach improves the efficiency and accuracy of extracting useful information from product reviews, helping users make informed decisions.
7. At least one computer-readable storage medium storing computer-executable instructions that, when executed, perform a method comprising: receiving, from a user, a text input expressing a question asking for recommendation of a product having a requested characteristic; generating, in response to the question, an answer that identifies a product having the requested characteristic for recommendation to the user; analyzing, using natural language analysis, a plurality of product reviews comprising natural language text evaluations of the product, including analyzing the natural language in at least one passage of text in at least one product review of the plurality of product reviews to determine whether the natural language in the at least one passage of text has a meaning indicating that the product has the requested characteristic, at least in part by converting the question to one or more hypotheses and determining whether the natural language in the at least one passage of text has a meaning that entails at least one of the one or more hypotheses; in response to determining via the natural language analysis that the natural language in the at least one passage of text has a meaning indicating that the product has the requested characteristic, identifying the at least one passage of text in the at least one product review as providing supporting evidence for the product in answer to the question; and presenting to the user, in response to the text input, the answer and the at least one passage in the at least one product review identified as providing supporting evidence for the answer.
The system recommends products based on user questions. It receives a text question asking for a product with a specific characteristic. It answers by identifying a product with that characteristic. It analyzes product reviews using natural language processing, examining if review passages say the product has the requested characteristic. It does this by converting the question into one or more hypotheses and checking if the review passages confirm those hypotheses. If a passage confirms the product has the characteristic, the system identifies it as supporting evidence. Finally, the system shows the recommended product and the supporting review passage to the user.
8. The at least one computer-readable storage medium of claim 7 , wherein the at least one product review comprises an evaluation of the product made by a purchaser of the product.
The computer-readable storage medium storing computer-executable instructions that, when executed, perform a method where the supporting review passage provided to the user in response to the text input expressing a question asking for recommendation of a product having a requested characteristic is an evaluation of the product made by a purchaser of the product.
9. The at least one computer-readable storage medium of claim 7 , wherein the at least one product review comprises an evaluation of the product made based on use of the product by an author of the at least one product review.
The computer-readable storage medium storing computer-executable instructions that, when executed, perform a method where the supporting review passage provided to the user in response to the text input expressing a question asking for recommendation of a product having a requested characteristic is an evaluation of the product made based on the reviewer's use of the product.
10. The at least one computer-readable storage medium of claim 7 , wherein the method further comprises retrieving the at least one passage in the at least one product review from at least one source selected from the group consisting of: user product reviews, expert product reviews, and social media.
The computer-readable storage medium storing computer-executable instructions that, when executed, perform a method further retrieves the supporting review passage provided to the user in response to the text input expressing a question asking for recommendation of a product having a requested characteristic from user product reviews, expert product reviews, or social media posts.
11. The at least one computer-readable storage medium of claim 7 , wherein the answer comprises information about the product, selected from the group consisting of: a name of the product, a brand of the product, a model identifier of the product, an image of the product, a price for the product, and identification of a merchant offering the product for sale.
The computer-readable storage medium storing computer-executable instructions that, when executed, perform a method where the product information provided to the user in response to the text input expressing a question asking for recommendation of a product having a requested characteristic, includes the product's name, brand, model identifier, image, price, or the merchant selling it.
12. The at least one computer-readable storage medium of claim 7 , wherein analyzing the plurality of product reviews further comprises: scoring passages in at least some of the plurality of product reviews based at least in part on strength of the passages' supporting evidence for the product in answer to the question; and selecting the at least one passage in the at least one product review for presentation to the user based at least in part on the scoring.
The computer-readable storage medium storing computer-executable instructions that, when executed, perform a method analyzes reviews by scoring review passages based on how strongly they support the product as an answer to the user's question. The system then selects the passage to show to the user based on this score. Specifically, the method comprises: receiving, from a user, a text input expressing a question asking for recommendation of a product having a requested characteristic; generating, in response to the question, an answer that identifies a product having the requested characteristic for recommendation to the user; analyzing, using natural language analysis, a plurality of product reviews comprising natural language text evaluations of the product, including analyzing the natural language in at least one passage of text in at least one product review of the plurality of product reviews to determine whether the natural language in the at least one passage of text has a meaning indicating that the product has the requested characteristic, at least in part by converting the question to one or more hypotheses and determining whether the natural language in the at least one passage of text has a meaning that entails at least one of the one or more hypotheses; in response to determining via the natural language analysis that the natural language in the at least one passage of text has a meaning indicating that the product has the requested characteristic, identifying the at least one passage of text in the at least one product review as providing supporting evidence for the product in answer to the question; and presenting to the user, in response to the text input, the answer and the at least one passage in the at least one product review identified as providing supporting evidence for the answer.
13. Apparatus comprising: at least one processor; and at least one storage medium storing processor-executable instructions that, when executed by the at least one processor, perform a method comprising: receiving, from a user, a text input expressing a question asking for recommendation of a product having a requested characteristic; generating, in response to the question, an answer that identifies a product having the requested characteristic for recommendation to the user; analyzing, using natural language analysis, a plurality of product reviews comprising natural language text evaluations of the product, including analyzing the natural language in at least one passage of text in at least one product review of the plurality of product reviews to determine whether the natural language in the at least one passage of text has a meaning indicating that the product has the requested characteristic, at least in part by converting the question to one or more hypotheses and determining whether the natural language in the at least one passage of text has a meaning that entails at least one of the one or more hypotheses; in response to determining via the natural language analysis that the natural language in the at least one passage of text has a meaning indicating that the product has the requested characteristic, identifying the at least one passage of text in the at least one product review as providing supporting evidence for the product in answer to the question; and presenting to the user, in response to the text input, the answer and the at least one passage in the at least one product review identified as providing supporting evidence for the answer.
The system recommends products based on user questions, using a processor and memory. It receives a text question asking for a product with a specific characteristic. It answers by identifying a product with that characteristic. It analyzes product reviews using natural language processing, examining if review passages say the product has the requested characteristic. It does this by converting the question into one or more hypotheses and checking if the review passages confirm those hypotheses. If a passage confirms the product has the characteristic, the system identifies it as supporting evidence. Finally, the system shows the recommended product and the supporting review passage to the user.
14. The apparatus of claim 13 , wherein the at least one product review comprises an evaluation of the product made by a purchaser of the product.
The apparatus that performs a method where the supporting review passage provided to the user in response to the text input expressing a question asking for recommendation of a product having a requested characteristic is an evaluation of the product made by a purchaser of the product.
15. The apparatus of claim 13 , wherein the at least one product review comprises an evaluation of the product made based on use of the product by an author of the at least one product review.
The apparatus that performs a method where the supporting review passage provided to the user in response to the text input expressing a question asking for recommendation of a product having a requested characteristic is an evaluation of the product made based on the reviewer's use of the product.
16. The apparatus of claim 13 , wherein the method further comprises retrieving the at least one passage in the at least one product review from at least one source selected from the group consisting of: user product reviews, expert product reviews, and social media.
The apparatus that performs a method further retrieves the supporting review passage provided to the user in response to the text input expressing a question asking for recommendation of a product having a requested characteristic from user product reviews, expert product reviews, or social media posts.
17. The apparatus of claim 13 , wherein the answer comprises information about the product, selected from the group consisting of: a name of the product, a brand of the product, a model identifier of the product, an image of the product, a price for the product, and identification of a merchant offering the product for sale.
The apparatus that performs a method where the product information provided to the user in response to the text input expressing a question asking for recommendation of a product having a requested characteristic, includes the product's name, brand, model identifier, image, price, or the merchant selling it.
18. The apparatus of claim 13 , wherein analyzing the plurality of product reviews further comprises: scoring passages in at least some of the plurality of product reviews based at least in part on strength of the passages' supporting evidence for the product in answer to the question; and selecting the at least one passage in the at least one product review for presentation to the user based at least in part on the scoring.
The apparatus that performs a method analyzes reviews by scoring review passages based on how strongly they support the product as an answer to the user's question. The system then selects the passage to show to the user based on this score. Specifically, the method comprises: receiving, from a user, a text input expressing a question asking for recommendation of a product having a requested characteristic; generating, in response to the question, an answer that identifies a product having the requested characteristic for recommendation to the user; analyzing, using natural language analysis, a plurality of product reviews comprising natural language text evaluations of the product, including analyzing the natural language in at least one passage of text in at least one product review of the plurality of product reviews to determine whether the natural language in the at least one passage of text has a meaning indicating that the product has the requested characteristic, at least in part by converting the question to one or more hypotheses and determining whether the natural language in the at least one passage of text has a meaning that entails at least one of the one or more hypotheses; in response to determining via the natural language analysis that the natural language in the at least one passage of text has a meaning indicating that the product has the requested characteristic, identifying the at least one passage of text in the at least one product review as providing supporting evidence for the product in answer to the question; and presenting to the user, in response to the text input, the answer and the at least one passage in the at least one product review identified as providing supporting evidence for the answer.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
December 18, 2014
May 16, 2017
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.